Instructions to use OraRL/Video-ORA-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OraRL/Video-ORA-4B with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="OraRL/Video-ORA-4B")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("OraRL/Video-ORA-4B")
model = AutoModelForMultimodalLM.from_pretrained("OraRL/Video-ORA-4B", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use OraRL/Video-ORA-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OraRL/Video-ORA-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OraRL/Video-ORA-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/OraRL/Video-ORA-4B

SGLang

How to use OraRL/Video-ORA-4B with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "OraRL/Video-ORA-4B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OraRL/Video-ORA-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "OraRL/Video-ORA-4B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OraRL/Video-ORA-4B",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use OraRL/Video-ORA-4B with Docker Model Runner:
```
docker model run hf.co/OraRL/Video-ORA-4B
```

Video-ORA-4B / code /tests /test_organize_evaluation_outputs.py

lyhisme

Add 4B model card, benchmark assets, and release code

0185029 verified about 12 hours ago

Raw

History Blame Contribute Delete

2.36 kB

	from __future__ import annotations

	import subprocess
	import sys
	from pathlib import Path

	SCRIPT = Path(__file__).parents[1] / "scripts" / "organize_evaluation_outputs.py"


	def _run(root: Path, *arguments: str) -> subprocess.CompletedProcess[str]:
	return subprocess.run(
	[sys.executable, str(SCRIPT), str(root), *arguments],
	check=False,
	capture_output=True,
	text=True,
	)


	def test_output_organizer_previews_then_groups_legacy_tasks(tmp_path: Path) -> None:
	root = tmp_path / "Video-ORA-9B"
	legacy_video_qa = root / "mvbench" / "base" / "run"
	legacy_spatial = root / "vsi" / "base" / "run"
	legacy_revsi = root / "revsi" / "base" / "run"
	legacy_tracking = root / "tracking" / "base" / "run"
	for directory in (
	legacy_video_qa,
	legacy_spatial,
	legacy_revsi,
	legacy_tracking,
	):
	directory.mkdir(parents=True)
	(directory / "summary.json").write_text("{}\n", encoding="utf-8")

	preview = _run(root)

	assert preview.returncode == 0
	assert "mvbench -> video_qa/mvbench" in preview.stdout
	assert legacy_video_qa.is_dir()

	applied = _run(root, "--apply")

	assert applied.returncode == 0
	assert (root / "video_qa/mvbench/base/run/summary.json").is_file()
	assert (root / "spatial_intelligence/vsi/base/run/summary.json").is_file()
	assert (root / "spatial_intelligence/revsi/base/run/summary.json").is_file()
	assert (legacy_tracking / "summary.json").is_file()
	assert not (root / "mvbench").exists()
	assert not (root / "vsi").exists()
	assert not (root / "revsi").exists()


	def test_output_organizer_refuses_to_overwrite_results(tmp_path: Path) -> None:
	root = tmp_path / "Video-ORA-9B"
	source = root / "mvbench" / "base" / "run"
	destination = root / "video_qa/mvbench/base/run"
	source.mkdir(parents=True)
	destination.mkdir(parents=True)
	(source / "summary.json").write_text('{"source": true}\n', encoding="utf-8")
	(destination / "summary.json").write_text(
	'{"destination": true}\n',
	encoding="utf-8",
	)

	completed = _run(root, "--apply")

	assert completed.returncode != 0
	assert "refusing to overwrite existing output" in completed.stderr
	assert (source / "summary.json").is_file()
	assert (destination / "summary.json").is_file()